Lucene search
+L

4 matches found

SUSE CVE
SUSE CVE
•added 2026/09/21 11:41 p.m.•6 views

SUSE CVE-2026-93989

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

4.3CVSS5.7AI score0.00202EPSS
SaveExploits0References3
Snyk
Snyk
•added 2026/09/20 1:35 a.m.•13 views

Improper Validation of Array Index

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Improper Validation of Array Index via SamplingParams.updatefromtokenizer, which fails to validate badwords token indices against the model's...

4.3CVSS5.5AI score0.00202EPSS
SaveExploits0References3
CVE
CVE
•added 2026/09/19 10:58 p.m.•38 views

CVE-2026-93989

The vLLM inference and serving engine (through version 0.29.0 ) is vulnerable to an Improper Validation of Array Index in the SamplingParams.update_from_tokenizer() function. A remote authenticated attacker can supply out-of-bounds bad_words token indices that fail to be validated against the mod...

4.3CVSS5.7AI score0.00202EPSS
SaveExploits0References5Affected Software1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/19 12:00 a.m.•1 views

CVE-2026-93989: Improper Validation of Array Index

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

4.3CVSS5.7AI score0.00202EPSS
SaveExploits0References4
Rows per page
Query Builder